For those of us who have been working in the world of conversational interfaces for some time, it’s exciting to see our art thrive but also surprising that conversation design is being talked about as if it’s something new.
The rise of new technologies means that conversation design is taking a new path and allowing us to rethink approaches to designing and using conversational interfaces. But when I think back to the start of my journey in the industry, some things really aren’t that new.
Back in the year 2000, one of the first conversational interface was with “Wildfire”, a speech-enabled voice assistant. Wildfire was pretty primitive, like it, manage your voicemail and call people in your contacts list. At that time, it seemed the thing that science fiction had been predicting for years.
It’s been 20 years and conversational landscape is still very young and full of potential.
Let us now better understand, What Conversation design actually is
What is Conversational Design
Conversation Design is the process of designing a natural, two-way interaction between a user and a system (via voice or text) based on the principles of human to human conversation. The conversation is the exchange of information by language.
Examples of conversational interfaces include voice interfaces, voice assistants, text-based conversational interfaces such as interactive SMS and chatbots.
Key Factors to keep in mind while designing a Conversational Design Interface
Understanding contextual dialog norms:
conversational interfaces should uphold various clients and various undertakings. This implies a ‘one-size fits all’ way to deal with discussion configuration doesn’t work. An IVR for medical services experts will be utilized in an alternate setting to clients of a chatbot who needs to discover the status of their request.
Our own examination has demonstrated that these various settings and client needs sway things like the convention of language expected, task needs, and even the particular words and expressions we use.
We have to comprehend those points of interest before we start the plan through client research (for example client interviews, call tuning in, and ethnography). This permits us to see how setting and the particular needs of the clients we’re planning for will affect the general discussion plan.
Co-operation: It means your chatbot can support a customer only if it cooperates and provides information the user is looking for. A cooperative system doesn’t require a user to have any specialized knowledge. For it to be efficient, your chatbot should be intuitive and respond using simple language.
Understanding contextual dialog norms:
conversational interfaces should uphold various clients and various undertakings. This implies a ‘one-size fits all’ way to deal with discussion configuration doesn’t work. An IVR for medical services experts will be utilized in an alternate setting to clients of a chatbot who needs to discover the status of their request.
Our own examination has demonstrated that these various settings and client needs sway things like the convention of language expected, task needs, and even the particular words and expressions we use. We have to comprehend those points of interest before we start the plan through client research (for example client interviews, call tuning in, and ethnography).
This permits us to see how setting and the particular needs of the clients we’re planning for will affect the general discussion plan.
Turn-based:
A Conversation requires listening and responding. Your chatbot has to engage users by letting them actively participate in a chat. For this, Avoid wordy replies and let users take their turn in the conversation.
Don’t send many replies one after another. This will spoil the experience as the user will have to scroll to get the whole message. In ChatBot you can set the speed at which your chatbot replies. This will help make your conversations more natural.
Moreover, always validate user answers so that they know your chatbot understands what they want. This will prevent misunderstandings and help avoid starting a conversation over.
When the conversation is finished, summarize what has been achieved during the chat and send the user a friendly goodbye message.
Error tolerant:
People don’t always understand what others are saying. Making mistakes is in our nature and very often people need to resolve misunderstandings while having a conversation to make it effective.
The same is true for chatbots. It’s normal that they don’t always understand the user. The point is to teach them to quickly resolve misunderstandings the way humans do.
To make your chatbot error-tolerant, try to anticipate common spelling mistakes first. Teach your chatbot these variations to improve its understanding.
Also, don’t make your chatbot reply just “I don’t understand”. It won’t fix the conversation. Instead, help users formulate their needs in a way that lets you respond to them.
You can simply ask or provide prompts in a form with predefined answers to indicate possible options. In ChatBot, you can also transfer a user to a human agent or let them create a ticket if a case goes beyond the scope of a chatbot’s capabilities.
Quick and clear:
There’s no better way to support conversation than to quickly answer questions. The research supports that claim: 69% of consumers say they prefer to use chatbots because they deliver quick answers to simple questions.
While creating your chatbot stories, try to avoid complex metaphors, idioms, and long ambiguous statements.
They slow down the conversation and take users away from where they need to be. Use simple language, don’t ask a user to choose many things at once, and get to the point.
Conclusion
Conversational interfaces are changing the way users interact with their devices every day.To make the user experience better and to make increase the efficacy of the interface, Conversational design factors will be key.
